Drone Detection by Neural Network Using GLCM and SURF Features

Ahmed, Tanzia; Rahman, Tanvir; Roy, Bir Ballav; Uddin, Jia

doi:10.52547/jist.9.33.15

Cited by 4 publications

(2 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Metode yang kami usulkan yaitu metode gray level co-occurence matrix (GLCM). Dimana metode GLCM dapat melakukan ekstraksi fitur-fitur tekstur pada lantai atau tangga turunan [9] [10]. Metode GLCM memiliki parameter sudut (ϴ) dan jarak (d).…”

Section: Gray Level Co-occurrence Matrixunclassified

Kernel Comparison on Support Vector Machine for Detecting Stairs Descent

Johan¹,

Wicaksono²,

Fauzi³

et al. 2022

Com, Engine, Sys, Sci

View full text Add to dashboard Cite

Terdapat 4 kernel yang dapat digunakan dalam klasifikasi Support Vector Machine dalam membuat hyperplane. Keempat kernel tersebut adalah linear, polynomial, gaussian dan sigmoid. Setiap kernel dapat menghasilkan akurasi yang berbeda-beda. Hal ini dikarenakan pengaruh sebaran data yang diklasifikasikan. Terdapat 2 kelas yang diklasifikasikan, yaitu lantai dan tangga turun. Dilakukan proses ekstraksi fitur tekstur terhadap citra lantai dan tangga turun menggunakan metode Gray Level Co-occurence Matrix. Terdapat 7 fitur dari GLCM yang dihasilkan pada proses ekstraksi fitur. Selanjutnya dilakukan klasifikasi menggunakan Support Vector Machine dengan mencoba setiap kernelnya. Dari hasil pengujian didapatkan kernel linear menghasilkan akurasi yang paling tinggi, yaitu 89%. Kernel sigmoid mendapatkan akurasi 84%. Kernel Gaussian mendapatkan akurasi sebesar 85%. Sedangkan kernel polynomial mendapatkan akurasi yang paling rendah yaitu 78%.

show abstract

Section: Gray Level Co-occurrence Matrixunclassified

Kernel Comparison on Support Vector Machine for Detecting Stairs Descent

Johan¹,

Wicaksono²,

Fauzi³

et al. 2022

Com, Engine, Sys, Sci

View full text Add to dashboard Cite

show abstract

“…Originally, they are polynomials Zernike polynomials known in mathematics and these polynomials are discriminated between them so that if applied to the image, they provide the program with features that aren't intertwined with each other and aren't affected by rotation and don't change the size [15].…”

Section: Zernike Moments Algorithmmentioning

confidence: 99%

A Comparative Study of Artificial Intelligence Algorithms Used for an Accurate Image Geometric Dimensions Recognition

Kaid¹,

Mahmoud²

2022

kuej

View full text Add to dashboard Cite

The process of distinguishing objects in digital images and recognizing them is a basic process in AI, in order to distinguish the object and determine its features. It has many uses in various engineering and medical fields. There is a great difficulty in recognizing digital images and distinguishing objects in them. This paper discusses some basic artificial intelligence techniques based on the geometric dimensions of the object in the image in order to recognize these objects and distinguish them from the background of the image. Where there is great difficulty in separating the object from its background, this paper presents the most accurate methods of programmatic application using Matlab environment to identify components in the image, its distinction, and its characteristics. The paper provides a comparison between these AI methods and chooses the most accurate one. AI recognition methods use various algorithms including algorithms based on color density and algorithms that depend on geometric dimensions such as Hue moment algorithms, Haralik features algorithms, and Zernike moment algorithms. In this paper these algorithms were applied to a group of images to extract the features of the object and the best one will be chosen with the aid of Matlab. The most accurate recognition process is chosen through building a digital library that contains many pictures and training the program on these images to recognize and distinguish the object in the image.

show abstract